stream_to_claude · CustomGPT MCP Server MCP: Risk & Policy

WHAT IT DOES

What stream_to_claude does on CustomGPT MCP Server

AI agents invoke stream_to_claude to trigger actions in CustomGPT MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why stream_to_claude needs a policy

This tool executes an external operation by streaming conversation data to an external AI service (Claude via CustomGPT). It is not a simple read/write but an active invocation of an external system that processes data and returns results. The effects depend on the conversation arguments passed.

From the tool's definition 'Stream conversation to Claude via CustomGPT with timeout prevention' — triggers an external streaming operation to Claude through CustomGPT, invoking an external AI service

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

stream_to_claude Rate-limited

stream_to_claude stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "stream_to_claude": {
      "limits": [
        {
          "counter": "stream_to_claude_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches CustomGPT MCP Server, so you can run agents against it safely.

FAQ

Questions about stream_to_claude

What does the stream_to_claude tool do? +

Stream conversation to Claude via CustomGPT with timeout prevention. It is categorised as a Execute tool in the CustomGPT MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on stream_to_claude? +

Register the CustomGPT MCP Server MCP server in PolicyLayer and add a rule for stream_to_claude: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches CustomGPT MCP Server. Nothing to install.

What risk level is stream_to_claude? +

stream_to_claude is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit stream_to_claude? +

Yes. Add a rate_limit block to the stream_to_claude rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block stream_to_claude completely? +

Set action: deny in the PolicyLayer policy for stream_to_claude. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides stream_to_claude? +

stream_to_claude is provided by the CustomGPT MCP Server MCP server (poll-the-people/customgpt-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.